Institution profile

Sun Yat-sen University

Academic institutionasia · cn
Official website
Research library2,353linked papers
Opportunities0open roles
Selected work

Representative Papers

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

Jan 03, 2024arXiv.org

Existing VideoQA datasets lack fine-grained modeling of professional sports actions, hindering effective reasoning for descriptive, temporal, causal, and counterfactual questions. To address this, we introduce Sports-QA—the first video question answering benchmark tailored to professional sports scenarios—covering multiple sports disciplines and four categories of complex reasoning tasks. Methodologically, we propose the Auto-Focus Transformer (AFT), which employs an attention-driven dynamic focusing mechanism to adaptively model multi-scale temporal information and integrates joint video–language representation learning. Extensive experiments demonstrate that AFT achieves state-of-the-art performance on Sports-QA, substantially outperforming general-purpose VideoQA models. This work constitutes the first systematic validation of an architecture explicitly designed for fine-grained sports action understanding and dynamic logical reasoning, establishing a new foundation for domain-specific VideoQA research.

10 citations2 influentialRead paper

Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation

Dec 17, 2023

This work addresses the semantic gap between natural language instructions and robotic physical actions to enhance the naturalness and reliability of human-robot collaboration. We propose the first four-dimensional taxonomy for language-conditioned robotic manipulation—comprising reward shaping, policy learning, neurosymbolic AI, and foundation model–driven approaches—and systematically analyze their fundamental limitations in generalization and safety. Integrating large language models (LLMs), vision-language models (VLMs), neurosymbolic reasoning, and multimodal semantic parsing, we develop a unified analytical framework spanning semantic extraction, environmental assessment, and auxiliary task design. Our analysis rigorously characterizes the performance boundaries of each paradigm for the first time, establishing theoretical foundations and concrete technical pathways toward safe, generalizable, and interpretable language-driven robotic systems.

10 citationsRead paper

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

Jan 23, 2026

This work addresses the high API costs and latency incurred by large language models in long-context encoding tasks, where existing compression methods often lack task awareness and risk disrupting code structure or discarding critical information. Inspired by human programmers’ “selective skimming” behavior, the authors propose an adaptive context pruning framework that introduces, for the first time, an explicit task-aware target prompting mechanism. This mechanism guides a lightweight (0.6B-parameter) neural skimmer to dynamically evaluate and retain only the most relevant code lines. Evaluated on four benchmarks including SWE-Bench Verified, the method achieves token compression rates of 23%–54%, with up to a 14.84× reduction on the LongCodeQA task, while incurring minimal performance degradation—demonstrating a strong balance between compression efficiency and semantic fidelity.

4 citations1 influentialRead paper

Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices

Oct 04, 2024

Deploying lightweight large language models (LLMs) such as Gemini Nano and LLaMA2-7B on commercial smartphones for privacy-sensitive, on-device inference remains challenging due to hardware-system bottlenecks under real-world constraints. Method: We conduct a systematic, multi-dimensional empirical evaluation across user-centric metrics (token throughput, time-to-first-token, power consumption), system resource utilization (memory bandwidth, GPU/NPU occupancy), and hardware-level controls (DVFS policies), benchmarking mainstream inference engines—including llama.cpp and MLC-LLM—on diverse mobile SoCs (Snapdragon, Dimensity, Apple A-series). Contribution/Results: This work is the first to identify and characterize hardware-system co-bottlenecks induced by LLM workloads on modern mobile SoCs, establishing memory bandwidth and energy efficiency as the primary limiting factors. Our analysis provides empirically grounded insights and actionable optimization pathways for on-device model compression, inference engine design, and AI-accelerator architecture development.

4 citations1 influentialRead paper

Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework

Jul 11, 2023IEEE journal of biomedical and health informatics

Poor cross-domain generalization and low stability of single-source-trained pancreatic segmentation models hinder clinical deployment. To address this, we propose a dual-path self-supervised learning framework: (1) a global path employs anatomy-guided contrastive learning to enhance intra-class compactness and inter-class separability in anatomical space; (2) a local path performs texture reconstruction on high-uncertainty regions to implicitly model local anatomical context. Without requiring additional annotations, our method jointly leverages structural priors and image generation constraints. Evaluated on three independent pancreatic datasets (467 cases), it achieves state-of-the-art performance—improving Dice scores by 3.2–5.8% over prior methods—and demonstrates significantly enhanced robustness and generalizability across multi-center and multi-device scenarios. This work provides a reliable technical foundation for clinical pancreatic image analysis.

4 citationsRead paper
Recent publications

Latest Papers